Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to average values or averages

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     useState
    -0.72
     Musk
    -0.72
     DialogInterface
    -0.72
    ̀n
    -0.71
     Betis
    -0.70
     Ruk
    -0.68
    selaer
    -0.68
     kasarigan
    -0.65
    ⓧ
    -0.65
    splan
    -0.64
    POSITIVE LOGITS
     оригіналу
    0.81
    पन
    0.76
    BufferException
    0.70
     arşivlendi
    0.69
    eradish
    0.69
    }}">
    0.67
     matrimon
    0.64
     Sándor
    0.64
     Hage
    0.63
    ætter
    0.63
    Act Density 0.029%

    No Known Activations